MeanVC2 Voice Conversion

by hugging-appsco.huggingface.hugging-apps/meanvc2-voice-conversion

Streaming zero-shot voice conversion with MeanVC2

  • Remote endpoint
  • 3 tools

Uptime

Checked  · every day

100%from 5 days of checks

Up without downtime on 5 of 5 days with data.

  • No downtime
  • Degraded
  • Down over 5 minutes
  • No data
  • Not checked yet

Response time

Median 1215 ms, slowest 5% 1272 ms for the handshake and the tool list, over 30 days.

1500 ms750 ms0

How far each check got

  • Reached the address 100%
  • Completed the handshake 100%
  • Listed its tools 100%

3 tools at the last answer.

Every day
DayResultChecksMedian
4 Nov (today)No downtime11259 ms
3 NovNo downtime1of 11256 ms
2 NovNo downtime1of 11198 ms
1 NovNo downtime1of 11058 ms
31 OctNo downtime21072 ms

A failure counts as down time only when a second check five minutes later fails too. How we check

Connect to the publisher's own endpoint

Add to resources/assets/config/mcp.json in the installed app:

{
  "mcpServers": {
    "meanvc2-voice-conversion": {
      "url": "https://hugging-apps-meanvc2-voice-conversion.hf.space/gradio_api/mcp/sse"
    }
  }
}

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

For agents: the install prompt

Every step above as one Markdown text, for an assistant installing it for you.

# Install the MCP server MeanVC2 Voice Conversion (`co.huggingface.hugging-apps/meanvc2-voice-conversion`)

Its page: https://plug.directory/servers/co.huggingface.hugging-apps/meanvc2-voice-conversion

It runs on the publisher's servers; the client connects to its URL.

Use the section for the person's client.

## Claude Desktop

Paste into Settings › Connectors › Add custom connector:

```text
https://hugging-apps-meanvc2-voice-conversion.hf.space/gradio_api/mcp/sse
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport sse meanvc2-voice-conversion https://hugging-apps-meanvc2-voice-conversion.hf.space/gradio_api/mcp/sse
```

## Cursor, Devin Desktop, LM Studio, Gemini CLI, oterm, ECA

Merge into the place for the person's client:

- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- Gemini CLI: ~/.gemini/settings.json
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project

```json
{
  "mcpServers": {
    "meanvc2-voice-conversion": {
      "url": "https://hugging-apps-meanvc2-voice-conversion.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "meanvc2-voice-conversion": {
      "type": "sse",
      "url": "https://hugging-apps-meanvc2-voice-conversion.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Zed

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Cline, AnythingLLM, Augment Code

Merge into the place for the person's client:

- Cline: cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers)
- AnythingLLM: anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory
- Augment Code: Augment Settings Panel – MCP section – Import from JSON (VS Code extension)

```json
{
  "mcpServers": {
    "meanvc2-voice-conversion": {
      "type": "sse",
      "url": "https://hugging-apps-meanvc2-voice-conversion.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "meanvc2-voice-conversion"
    type: sse
    url: "https://hugging-apps-meanvc2-voice-conversion.hf.space/gradio_api/mcp/sse"
```

## Goose

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Codex

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## mcp-client-cli, TUUI, BoltAI, Bob Shell, Kiro, Kiro CLI

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Agenvoy

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Amp

Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):

```json
{
  "amp.mcpServers": {
    "meanvc2-voice-conversion": {
      "url": "https://hugging-apps-meanvc2-voice-conversion.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.

Tools 3

  • meanvc2_voice_conversion_convert Convert the voice in `source_audio` to the speaker heard in `reference_audio`. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: (sample_rate, waveform) tuple with the converted 16 kHz audio.
  • meanvc2_voice_conversion_prep_live_reference Prepare a live session from an uploaded/recorded target-voice reference. Called from a regular ``gr.Audio`` component in the Live tab (upload or mic-record — NOT streaming). It extracts the 256-d speaker embedding once from the provided reference file and stashes it in a fresh live session, returning that session id so the custom mic-streaming HTML component can use it for the live conversion loop. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: A session id string (empty if no reference was provided).
  • meanvc2_voice_conversion_run_live_session One long-lived GPU session that streams live voice conversion. This is the SDXL-Turbo continuous-generator loop adapted to audio. It holds a *single* ZeroGPU allocation for the whole session (instead of forking a fresh worker per mic slice) and, for the full session window, drains the per-session input queue that ``live_push`` fills with raw mic audio, accumulates it in a buffer, converts it once enough has piled up, and writes the converted audio to the per-session output queue for ``live_pull`` to hand back to the browser. Nothing that arrives is dropped: short slices are buffered until a full MeanVC2 slice can be produced, and any tail shorter than one slice is kept for the next iteration.

From Hugging Face Spaces. Report a problem